Processing channel state information (CSI) to determine characteristics of a space between wireless access points

Abstract

A computing system includes a storage device and processing circuitry having access to the storage device. The processing circuitry is configured to receive a sequence of channel state information (CSI) samples, and calculate, based on the sequence of CSI samples, frequency domain information including a set of frequency domain values for each frequency band of a plurality of frequency bands. The processing circuitry is further configured to select a set of frequency bands of the plurality of frequency bands; and calculate, based on the set of frequency domain values for each frequency band of the set of frequency bands, a set of similarity values. Additionally, the processing circuitry is configured to determine, based on the set of similarity values, information indicative of one or more characteristics of a space between a first computing device and a second computing device, and perform an action based on the information.

What is claimed is: 
     
       1. A computing system comprising:
 a storage device; and 
 processing circuitry having access to the storage device and configured to:
 receive a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples correspond to a communication channel between a first computing device and a second computing device; 
 calculate, based on the sequence of CSI samples, frequency domain information including a set of frequency domain values for each frequency band of a plurality of frequency bands; 
 select a set of frequency bands of the plurality of frequency bands; 
 calculate, based on the set of frequency domain values for each frequency band of the set of frequency bands, a set of similarity values, wherein each similarity value of the set of similarity values corresponds to the set of frequency domain values for the respective frequency band of the set of frequency bands; 
 determine, based on the set of similarity values, information indicative of one or more characteristics of a space between the first computing device and the second computing device; and 
 perform an action based on the information. 
 
 
     
     
       2. The computing system of  claim 1 ,
 wherein to receive the sequence of CSI samples, the processing circuitry is configured to receive a sequence of sets of CSI values, wherein each set of CSI values of the sequence of sets of CSI values corresponds to a respective CSI sample of the sequence of CSI samples, wherein the sequence of sets of CSI values correspond to a set of CSI value sequences, 
 wherein to calculate the frequency domain information, the processing circuitry is configured to compute a set of discrete Fourier transforms (DFTs) each corresponding to a respective CSI value sequence of the set of CSI value sequences, wherein each DFT of the set of DFTs includes a plurality of DFT values each indicating a parameter of a respective frequency band of a plurality of frequency bands, and 
 wherein the processing circuitry is configured to calculate the set of similarity values based on a set of DFT values for each frequency band of the set of frequency bands. 
 
     
     
       3. The computing system of  claim 2 , wherein the sequence of sets of CSI values include one or more complex numbers each including an amplitude value and a phase value. 
     
     
       4. The computing system of  claim 2 , wherein to calculate the set of similarity values, the processing circuitry is configured to:
 identify a matrix of DFT values comprising a set of rows and a set of columns, wherein each row of the set of rows includes a row set of DFT values corresponding to a respective DFT of the set of DFTs, and wherein each column of the set of columns includes a column set of DFT values corresponding to a respective frequency band of the set of frequency bands; and 
 compute, for each frequency band of the set of frequency bands, a similarity value of the set of similarity values based on the column set of DFT values in the respective column of the set of columns. 
 
     
     
       5. The computing system of  claim 4 , wherein to compute each similarity value of the set of similarity values, the processing circuitry is configured to compute a similarity measure that quantifies a similarity between the one or more DFT values for the respective frequency band of the set of frequency bands. 
     
     
       6. The computing system of  claim 5 , wherein the similarity measure represents any one or combination of a Euclidean Similarity, a cosine similarity, a Minkowski similarity, and a Jaccard similarity. 
     
     
       7. The computing system of  claim 1 , wherein to determine the information indicative of the one or more characteristics of the space between the first computing device and the second computing device, the processing circuitry is configured to:
 execute a trained machine learning model, wherein the set of similarity values represent inputs to the machine learning model; and 
 receive, as an output from the machine learning model, the information indicative of the one or more characteristics of the space between the first computing device and the second computing device. 
 
     
     
       8. The computing system of  claim 7 , wherein the information indicative of the one or more characteristics of the space between the first computing device and the second computing device comprises any one or combination of:
 information indicative of whether movement is present in the space during a period of time corresponding to the sequence of CSI samples; 
 information indicative of an identity of one or more objects or persons moving in the space during the period of time corresponding to the sequence of CSI samples; and 
 information indicative of a location of one or more objects or persons moving in the space during the period of time corresponding to the sequence of CSI samples. 
 
     
     
       9. The computing system of  claim 1 , wherein to select the set of frequency bands of the plurality of frequency bands, the processing circuitry is configured to select one or more frequency bands that are lower than a mean frequency of the plurality of frequency bands. 
     
     
       10. The computing system of  claim 1 , wherein to select the set of frequency bands of the plurality of frequency bands, the processing circuitry is configured to select the set of frequency bands to include the lowest 20% of frequencies in the plurality of frequency bands. 
     
     
       11. The computing system of  claim 1 , wherein the second computing device comprises the processing circuitry and the storage device, and wherein the second computing device is configured to receive, from the first computing device, each CSI sample of the sequence of CSI samples. 
     
     
       12. The computing system of  claim 1 , wherein the first computing device comprises a first Wi-Fi access point, and wherein the second computing device comprises a second Wi-fi Access Point. 
     
     
       13. A method comprising:
 receiving, by processing circuitry having access to a storage device, a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples correspond to a communication channel between a first computing device and a second computing device; 
 calculating, by the processing circuitry based on the sequence of CSI samples, frequency domain information including a set of frequency domain values for each frequency band of a plurality of frequency bands; 
 selecting, by the processing circuitry, a set of frequency bands of the plurality of frequency bands; 
 calculating, by the processing circuitry based on the set of frequency domain values for each frequency band of the set of frequency bands, a set of similarity values, wherein each similarity value of the set of similarity values corresponds to the set of frequency domain values for the respective frequency band of the set of frequency bands; 
 determining, by the processing circuitry based on the set of similarity values, information indicative of one or more characteristics of a space between the first computing device and the second computing device; and 
 performing, by the processing circuitry, an action based on the information. 
 
     
     
       14. The method of  claim 13 ,
 wherein receiving the sequence of CSI samples comprises receiving a sequence of sets of CSI values, wherein each set of CSI values of the sequence of sets of CSI values corresponds to a respective CSI sample of the sequence of CSI samples, wherein the sequence of sets of CSI values correspond to a set of CSI value sequences, 
 wherein calculating the frequency domain information comprises computing a set of discrete Fourier transforms (DFTs) each corresponding to a respective CSI value sequence of the set of CSI value sequences, wherein each DFT of the set of DFTs includes a plurality of DFT values each indicating a parameter of a respective frequency band of a plurality of frequency bands, and 
 wherein the method further comprises calculating the set of similarity values based on a set of DFT values for each frequency band of the set of frequency bands. 
 
     
     
       15. The method of  claim 14 , wherein calculating the set of similarity values comprises:
 identifying a matrix of DFT values comprising a set of rows and a set of columns, wherein each row of the set of rows includes a row set of DFT values corresponding to a respective DFT of the set of DFTs, and wherein each column of the set of columns includes a column set of DFT values corresponding to a respective frequency band of the set of frequency bands; and 
 computing, for each frequency band of the set of frequency bands, a similarity value of the set of similarity values based on the column set of DFT values in the respective column of the set of columns. 
 
     
     
       16. The method of  claim 15 , wherein computing each similarity value of the set of similarity values comprises computing a similarity measure that quantifies a similarity between the one or more DFT values for the respective frequency band of the set of frequency bands. 
     
     
       17. The method of  claim 13 , wherein determining the information indicative of the one or more characteristics of the space between the first computing device and the second computing device comprises:
 executing a trained machine learning model, wherein the set of similarity values represent inputs to the machine learning model; and 
 receiving, as an output from the machine learning model, the information indicative of the one or more characteristics of the space between the first computing device and the second computing device. 
 
     
     
       18. The method of  claim 13 , wherein selecting the set of frequency bands of the plurality of frequency bands comprises selecting one or more frequency bands that are lower than a mean frequency of the plurality of frequency bands. 
     
     
       19. The method of  claim 13 , wherein selecting the set of frequency bands of the plurality of frequency bands comprises selecting the set of frequency bands to include the lowest 20% of frequencies in the plurality of frequency bands. 
     
     
       20. A non-transitory computer-readable medium comprising instructions that, when executed by a processor, causes the processor to:
 receive a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples correspond to a communication channel between a first computing device and a second computing device; 
 calculate, based on the sequence of CSI samples, frequency domain information including a set of frequency domain values for each frequency band of a plurality of frequency bands; 
 select a set of frequency bands of the plurality of frequency bands; 
 calculate, based on the set of frequency domain values for each frequency band of the set of frequency bands, a set of similarity values, wherein each similarity value of the set of similarity values corresponds to the set of frequency domain values for the respective frequency band of the set of frequency bands; 
 determine, based on the set of similarity values, information indicative of one or more characteristics of a space between the first computing device and the second computing device; and 
 perform an action based on the information.